Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add randommonicle/claude-skills --skill unslop-codegit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/randommonicle/claude-skills/unslop-code)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/unslop-code"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-code/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/unslop-code"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/unslop-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00218 | $0.02325 |
| Opus 5 | $0.00109 | $0.01162 |
| Sonnet 5 | $0.00044 | $0.00465 |
| Haiku 4.5 | $0.00022 | $0.00232 |
Grade A, and why
unslop-code scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
unslop-code
Read this first, because the most common misunderstanding sinks the whole thing.
This skill does not write good code for you, and it has no house style. It does two narrow things. It removes the specific surface cues that make code read as machine-generated, and it points you at the deeper tells (the ones that ship bugs) that no scanner can catch. Whether the code is correct, well-factored, and right for the problem is still your call. A guardrail is not an engineer.
The trap to avoid (this is the whole point)
The surface tells are the cheap part. You can strip every emoji, delete every // rest of your code stub, and fix every bare except, and still ship a file that is tutorial-shaped, calls a
made-up API, over-engineers a simple task, and ignores how the rest of the repo works. Those
are the loudest tells in the data, and a clean lint hides them. The verified ranking is blunt
about it: boilerplate (18.6%), hallucinated APIs (11.2%), and over-engineering (7.8%) tower
over the cosmetic stuff (emoji 3.9%, verbose names 0.4%). So removing surface tells is the easy
40% of the job, not the job. Do not mistake a clean scan for clean code.
Two kinds of tell: bugs and cosmetics
Sort every tell by one question before any other: is the code wrong, or does it just look machine-made?
- Bugs. Swallowed and over-broad exception handling eats the failure you needed. A
hallucinated or nonexistent API will not run. A
// rest of your codestub means the file is unfinished. These are not style. Fix them because the code is broken, the same way you would fix any bug, whether or not anyone ever suspected AI. - Cosmetics. Emoji, leftover chat artifacts, narrating comments, generic and over-verbose names. These are the model's chat voice leaking into the file. Worth removing because they read as AI, but nothing breaks if one survives. This is the lighter class.
The scanner reports both, tagged with the class; the catalog tags every tell the same way. The point of the split: do not spend an audit polishing cosmetics while a swallowed error or a made-up call ships. (There is a third class, substance: tutorial shape, over-engineering, and repo mismatch. It is wrong for the job rather than locally broken, and needs a human reading the diff. See references/tells.md.)
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 163 lines · 218 tokens per session scan A 118b4e3a2163
unslop-code is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 218 tokens to every session and 2,325 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…